Automatic calibration of time of flight based non-line-of-sight reconstruction
This addresses the need for reliable non-line-of-sight imaging in applications like robotics or surveillance by enabling autocalibration, though it is incremental as it builds on existing reconstruction methods.
The paper tackles the problem of calibration errors in time-of-flight non-line-of-sight imaging, which can cause reconstruction failures, by proposing a differentiable forward model that jointly recovers scene albedo and calibration parameters using gradient descent, demonstrating robust reconstructions on simulated and real data where other state-of-the-art methods fail.
Time of flight based Non-line-of-sight (NLOS) imaging approaches require precise calibration of illumination and detector positions on the visible scene to produce reasonable results. If this calibration error is sufficiently high, reconstruction can fail entirely without any indication to the user. In this work, we highlight the necessity of building autocalibration into NLOS reconstruction in order to handle mis-calibration. We propose a forward model of NLOS measurements that is differentiable with respect to both, the hidden scene albedo, and virtual illumination and detector positions. With only a mean squared error loss and no regularization, our model enables joint reconstruction and recovery of calibration parameters by minimizing the measurement residual using gradient descent. We demonstrate our method is able to produce robust reconstructions using simulated and real data where the calibration error applied causes other state of the art algorithms to fail.